Avoid holding ashmem_mutex across code that can page fault. Page faults
grab the mmap_sem for the process, which are also held by mmap calls
prior to calling ashmem_mmap, which locks ashmem_mutex. The reversed
order of locking between the two can deadlock.
The calls that can page fault are read() and the ASHMEM_SET_NAME and
ASHMEM_GET_NAME ioctls. Move the code that accesses userspace pages
outside the ashmem_mutex.
Cc: Colin Cross <ccross@android.com>
Cc: Android Kernel Team <kernel-team@android.com>
Signed-off-by: Todd Poynor <toddpoynor@google.com>
[jstultz: minor commit message tweaks]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Before this change, a timeline would only be removed from the timeline
list *after* the sync driver had its release_obj() called. However, the
driver's release_obj() may free resources needed by print_obj().
Although the timeline list is locked when print_obj() is called, it is
not locked when release_obj() is called. If one CPU was in print_obj()
when another was in release_obj(), the print_obj() may make unsafe
accesses.
It is not actually necessary to hold the timeline list lock when calling
release_obj() if the call is made after the timeline is unlinked from
the list, since there is no possibility another thread could be in --
or enter -- print_obj() for that timeline.
This change moves the release_obj() call to after the timeline is
unlinked, preventing the above race from occurring.
Cc: Colin Cross <ccross@android.com>
Cc: Android Kernel Team <kernel-team@android.com>
Signed-off-by: Alistair Strachan <alistair.strachan@imgtec.com>
[jstultz: minor commit subject tweak]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The ION_DUMMY option is bool, and hence this code is either
present or absent. It will never be modular, so using
module_init as an alias for __initcall is rather misleading.
Fix this up now, so that we can relocate module_init from
init.h into module.h in the future. If we don't do this, we'd
have to add module.h to obviously non-modular code, and that
would be a worse thing.
Note that direct use of __initcall is discouraged, vs. one
of the priority categorized subgroups. As __initcall gets
mapped onto device_initcall, our use of device_initcall
directly in this change means that the runtime impact is
zero -- it will remain at level 6 in initcall ordering.
Cc: Colin Cross <ccross@android.com>
Cc: Jesse Barker <jesse.barker@arm.com>
Cc: Android Kernel Team <kernel-team@android.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
use ARRAY_SIZE to count number of heaps in static array
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Need add "linux/io.h" to pass compiling under metag architecture with
allmodconfig (which use the default 'virt_to_phys'), the related error:
CC drivers/staging/android/ion/ion_dummy_driver.o
drivers/staging/android/ion/ion_dummy_driver.c: In function 'ion_dummy_init':
drivers/staging/android/ion/ion_dummy_driver.c:81: error: implicit declaration of function 'virt_to_phys'
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Included is the patch previously set as the fourth round for 3.13 which was
to late to be appropriate.
* Another endian fix (ad799x adc) due to missuse of the IIO_ST macro (which
is going away very shortly)
* A reversed error check in ad5933 which will make the probe fail.
* A buffer overflow in the example code in the documentation.
* ad799x was freeing an irq that might or might not have been requested.
* tsl2563 was checking the wrong element of chan_spec for modifiers. Thus some
sysfs reads would give the wrong values.
* A missing dependency on HAS_IOMEM in spear_adc and lpc32xx was causing some
test build failures (on s390 and perhaps elsewhere).
I also have a few fixes queued up for things that went in during the 3.14
merge window which will follow as a separate pull request (to avoid rebasing
my tree).
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=otUr
-----END PGP SIGNATURE-----
Merge tag 'iio-fixes-for-3.14a' of git://git.kernel.org/pub/scm/linux/kernel/git/jic23/iio into staging-linus
Jonathan writes:
First set of IIO fixes for the 3.14 cycle.
Included is the patch previously set as the fourth round for 3.13 which was
to late to be appropriate.
* Another endian fix (ad799x adc) due to missuse of the IIO_ST macro (which
is going away very shortly)
* A reversed error check in ad5933 which will make the probe fail.
* A buffer overflow in the example code in the documentation.
* ad799x was freeing an irq that might or might not have been requested.
* tsl2563 was checking the wrong element of chan_spec for modifiers. Thus some
sysfs reads would give the wrong values.
* A missing dependency on HAS_IOMEM in spear_adc and lpc32xx was causing some
test build failures (on s390 and perhaps elsewhere).
I also have a few fixes queued up for things that went in during the 3.14
merge window which will follow as a separate pull request (to avoid rebasing
my tree).
It makes no sense to inline a rarely used function meant for debugging
only that is called a total of five times in the main evaluation loop.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
cbnz/tbnz don't update the condition flags, so remove the "cc" clobbers
from inline asm blocks that only use these instructions to implement
conditional branches.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The 'active' sysfs attribute should refer to the currently active tty
devices the console is running on, not the currently active console.
The console structure doesn't refer to any device in sysfs, only the tty
the console is running on has. So we need to print out the tty names in
'active', not the console names.
This resolves an issue on s390 platforms in determining the correct
console device to use.
Cc: Lennart Poettering <lennart@poettering.net>
Cc: Kay Sievers <kay@vrfy.org>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Werner Fink <werner@suse.de>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
3GPP TS 07.10 states in section 5.4.6.3.7:
"The length byte contains the value 2 or 3 ... depending on the break
signal." The break byte is optional and if it is sent, the length is
3. In fact the driver was not able to work with modems that send this
break byte in their modem status control message. If the modem just
sends the break byte if it is really set, then weird things might
happen.
The code for deconding the modem status to the internal linux
presentation in gsm_process_modem has already a big comment about
this 2 or 3 byte length thing and it is already able to decode the
brk, but the code calling the gsm_process_modem function in
gsm_control_modem does not encode it and hand it over the right way.
This patch fixes this.
Without this fix if the modem sends the brk byte in it's modem status
control message the driver will hang when opening a muxed channel.
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The HVC_OPAL/RTAS/UDBG/XEN options are all bool, and hence their support
is either present or absent. It will never be modular, so using
module_init as an alias for __initcall is rather misleading.
Fix this up now, so that we can relocate module_init from
init.h into module.h in the future. If we don't do this, we'd
have to add module.h to obviously non-modular code, and that
would be a worse thing.
Note that direct use of __initcall is discouraged, vs. one
of the priority categorized subgroups. As __initcall gets
mapped onto device_initcall, our use of device_initcall
directly in this change means that the runtime impact is
zero -- it will remain at level 6 in initcall ordering.
Also the __exitcall functions have been outright deleted since
they are only ever of interest to UML, and UML will never be
using any of this code.
Cc: Richard Weinberger <richard@nod.at>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Acked-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The Kconfig symbol MAX_RAW_DEVS is meant to be between 1 and 65536. But
those boundaries are not enforced by its Kconfig entry.
Note that MAX_RAW_DEVS is used to set MAX_RAW_MINORS in
drivers/char/raw.c. If one would accidentally set MAX_RAW_DEVS to an
invalid value, that invalid value will actually end up being used in
raw_init().
So add an appropriate range to this Kconfig entry.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
bind_get() checks the device number it is called with. It uses
MAX_RAW_MINORS for the upper bound. But MAX_RAW_MINORS is set at compile
time while the actual number of raw devices can be set at runtime. This
means the test can either be too strict or too lenient. And if the test
ends up being too lenient bind_get() might try to access memory beyond
what was allocated for "raw_devices".
So check against the runtime value (max_raw_minors) in this function.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Acked-by: Jan Kara <jack@suse.cz>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When the guest attempts to connect with the host when there may already be a
connection with the host (as would be the case during the kdump/kexec path),
it is difficult to guarantee timely response from the host. Starting with
WS2012 R2, the host supports this ability to re-connect with the host
(explicitly to support kexec). Prior to responding to the guest, the host
needs to ensure that device states based on the previous connection to
the host have been properly torn down. This may introduce unbounded delays.
To deal with this issue, don't do a timed wait during the initial connect
with the host.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
During the initial VMBUS connect phase, starting with WS2012 R2, we should
specify the VPCU in the guest that should receive the notification. Fix this
issue. This fix is required to properly connect to the host in the kexeced
kernel.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Cc: <stable@vger.kernel.org> [3.9+]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix access to uninitialized data for end interval elements. The
element data part is uninitialized in interval end elements.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Add DT file for new SAMA5D3 Xplained board.
This board is based on Atmel's SAMA5D36 Cortex-A5 SoC.
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Document the clock properties required by the spi-atmel driver.
Signed-off-by: Boris BREZILLON <b.brezillon@overkiz.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Document the clock properties required by the atmel-mci driver.
Signed-off-by: Boris BREZILLON <b.brezillon@overkiz.com>
Acked-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
The hclk clock of the ohci node is referencing udphs_clk instead of
uhphs_clk.
Signed-off-by: Boris BREZILLON <b.brezillon@overkiz.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
In order to ensure the correct width cycles on the VME bus, the VME bridge
drivers implement an algorithm to utilise the largest possible width reads and
writes whilst maintaining natural alignment constraints. The algorithm
currently looks at the start address rather than the current read/write address
when determining whether a 16-bit width cycle is required to get to 32-bit
alignment. This results in incorrect alignment,
Reported-by: Jim Strouth <james.strouth@ge.com>
Tested-by: Jim Strouth <james.strouth@ge.com>
Signed-off-by: Martyn Welch <martyn.welch@ge.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Clear write callbacks sitting in write_waiting list on reset.
Otherwise these callbacks are left dangling and cause memory leak.
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Apparently it's broken in the exact same way as the gmbus irq. For
reference of the full story see
commit c12aba5aa0
Author: Jiri Kosina <jkosina@suse.cz>
Date: Tue Mar 19 09:56:57 2013 +0100
drm/i915: stop using GMBUS IRQs on Gen4 chips
The effect is that we have a storm of unclaimed interrupts on the
legacy irq line. If that one is used by a different device then the
kernel will complain and rather quickly kill the irq source. Which
breaks any device trying to actually use the legacy irq line.
This regression has been introduced
commit 4aeebd7443
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu Oct 31 09:53:36 2013 +0100
drm/i915: dp aux irq support for g4x/vlv
Note that disabling MSI works around the issue, but we can't do that
since apparently then the hw will miss interrupts. At least if
relevant comments in i915_irq.c are accurate.
v2: Cross-reference dp aux and gmbus gen4 comments.
v3: Consolidate harder into i915_drv.h as suggested by Chris.
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reported-and-tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Because we use a list_head in the bo to track it's position in a submit,
we need to serialize at a higher layer. Otherwise there are problems
when multiple contexts are SUBMIT'ing in parallel cmdstreams referencing
a shared bo.
Signed-off-by: Rob Clark <robdclark@gmail.com>
This patch fixes several things which related to the handling of
end interval elements:
* Chain use underflow with intervals and map: If you add a rule
using intervals+map that introduces a loop, the error path of the
rbtree set decrements the chain refcount for each side of the
interval, leading to a chain use counter underflow.
* Don't copy the data part of the end interval element since, this
area is uninitialized and this confuses the loop detection code.
* Don't allocate room for the data part of end interval elements
since this is unused.
So, after this patch the idea is that end interval elements don't
have a data part.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Patrick McHardy <kaber@trash.net>
This combination is not allowed since end interval elements cannot
contain data.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Patrick McHardy <kaber@trash.net>
The very same fixup is needed to make the mic on Sony VAIO Pro 11
working as well as VAIO Pro 13 model.
Reported-and-tested-by: Hendrik-Jan Heins <hjheins@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The current code for controlling mic mute LED in patch_sigmatel.c
blindly assumes that there is a single capture switch. But, there can
be multiple multiple ones, and each of them flips the state, ended up
in an inconsistent state.
For fixing this problem, this patch adds kcontrol to be passed to the
hook function so that the callee can check which switch is being
accessed. In stac_capture_led_hook(), the state is checked as a
bitmask, and turns on the LED when all capture switches are off.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Since the commit [595fe1b702: ALSA: hda - Make
CONFIG_SND_HDA_CODEC_* tristate], the kconfig variables for the
generic parser and codec drivers can be "m" instead of boolean, but
some codes are left unchanged to check only #ifdef
CONFIG_SND_HDA_CODEC_XXX, which is no longer true for modules.
This patch fixes them by replacing with IS_ENABLED() macros.
Fixes: 595fe1b702 ('ALSA: hda - Make CONFIG_SND_HDA_CODEC_* tristate')
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=70161
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Currently Connect-IB does not support blocking multicast loopback, so
don't set IB_DEVICE_BLOCK_MULTICAST_LOOPBACK in the device caps.
Reported by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Commit c1be5232d2 ("Fix micro UAR allocator") broke binary compatibility
between libmlx5 and mlx5_ib since it defines a different value to the number
of micro UARs per page, leading to wrong calculation in libmlx5. This patch
defines struct mlx5_ib_alloc_ucontext_req_v2 as an extension to struct
mlx5_ib_alloc_ucontext_req. The extended size is determined in mlx5_ib_alloc_ucontext()
and in case of old library we use uuarn 0 which works fine -- this is
acheived due to create_user_qp() falling back from high to medium then to
low class where low class will return 0. For new libraries we use the
more sophisticated allocation algorithm.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Yann Droneaud <ydroneaud@opteya.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Fix the RC QPs send queue overhead computation to take into account
two additional segments in the WQE which are needed for registration
operations.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
TCP pacing depends on an accurate srtt estimation.
Current srtt estimation is using jiffie resolution,
and has an artificial offset of at least 1 ms, which can produce
slowdowns when FQ/pacing is used, especially in DC world,
where typical rtt is below 1 ms.
We are planning a switch to usec resolution for linux-3.15,
but in the meantime, this patch removes the 1 ms offset.
All we need is to have tp->srtt minimal value of 1 to differentiate
the case of srtt being initialized or not, not 8.
The problematic behavior was observed on a 40Gbit testbed,
where 32 concurrent netperf were reaching 12Gbps of aggregate
speed, instead of line speed.
This patch also has the effect of reporting more accurate srtt and send
rates to iproute2 ss command as in :
$ ss -i dst cca2
Netid State Recv-Q Send-Q Local Address:Port
Peer Address:Port
tcp ESTAB 0 0 10.244.129.1:56984
10.244.129.2:12865
cubic wscale:6,6 rto:200 rtt:0.25/0.25 ato:40 mss:1448 cwnd:10 send
463.4Mbps rcv_rtt:1 rcv_space:29200
tcp ESTAB 0 390960 10.244.129.1:60247
10.244.129.2:50204
cubic wscale:6,6 rto:200 rtt:0.875/0.75 mss:1448 cwnd:73 ssthresh:51
send 966.4Mbps unacked:73 retrans:0/121 rcv_space:29200
Reported-by: Vytautas Valancius <valas@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 93d8bf9fb8 ("bridge: cleanup netpoll code") introduced
a check in br_netpoll_enable(), but this check is incorrect for
br_netpoll_setup(). This patch moves the code after the check
into __br_netpoll_enable() and calls it in br_netpoll_setup().
For br_add_if(), the check is still needed.
Fixes: 93d8bf9fb8 ("bridge: cleanup netpoll code")
Cc: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Tested-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
sock_alloc_send_pskb() & sk_page_frag_refill()
have a loop trying high order allocations to prepare
skb with low number of fragments as this increases performance.
Problem is that under memory pressure/fragmentation, this can
trigger OOM while the intent was only to try the high order
allocations, then fallback to order-0 allocations.
We had various reports from unexpected regressions.
According to David, setting __GFP_NORETRY should be fine,
as the asynchronous compaction is still enabled, and this
will prevent OOM from kicking as in :
CFSClientEventm invoked oom-killer: gfp_mask=0x42d0, order=3, oom_adj=0,
oom_score_adj=0, oom_score_badness=2 (enabled),memcg_scoring=disabled
CFSClientEventm
Call Trace:
[<ffffffff8043766c>] dump_header+0xe1/0x23e
[<ffffffff80437a02>] oom_kill_process+0x6a/0x323
[<ffffffff80438443>] out_of_memory+0x4b3/0x50d
[<ffffffff8043a4a6>] __alloc_pages_may_oom+0xa2/0xc7
[<ffffffff80236f42>] __alloc_pages_nodemask+0x1002/0x17f0
[<ffffffff8024bd23>] alloc_pages_current+0x103/0x2b0
[<ffffffff8028567f>] sk_page_frag_refill+0x8f/0x160
[<ffffffff80295fa0>] tcp_sendmsg+0x560/0xee0
[<ffffffff802a5037>] inet_sendmsg+0x67/0x100
[<ffffffff80283c9c>] __sock_sendmsg_nosec+0x6c/0x90
[<ffffffff80283e85>] sock_sendmsg+0xc5/0xf0
[<ffffffff802847b6>] __sys_sendmsg+0x136/0x430
[<ffffffff80284ec8>] sys_sendmsg+0x88/0x110
[<ffffffff80711472>] system_call_fastpath+0x16/0x1b
Out of Memory: Kill process 2856 (bash) score 9999 or sacrifice child
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, to make netconsole start over IPv6, the source address
needs to be specified. Without a source address, netpoll_parse_options
assumes we're setting up over IPv4 and the destination IPv6 address is
rejected.
Check if the IP version has been forced by a source address before
checking for a version mismatch when parsing the destination address.
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit ee45fd92c7 ("sfc: Use TX PIO
for sufficiently small packets") introduced the following warning:
drivers/net/ethernet/sfc/tx.c: In function 'efx_enqueue_skb':
drivers/net/ethernet/sfc/tx.c:432:1: warning: label 'finish_packet' defined but not used
Stick the label inside the same #ifdef that the code which calls
it uses. Note that this is only seen for arch that do not set
ARCH_HAS_IOREMAP_WC, such as arm, mips, sparc, ..., as the others
enable the write combining code and hence use the label.
Cc: Jon Cooper <jcooper@solarflare.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Acked-by: Shradha Shah <sshah@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It seems like this function was intended to have special handling for
urb statuses of -ENOENT and -ECONNRESET. But now it just prints some
debugging and returns at the start of the function.
I have removed the dead code, it's still in the git history if anyone
wants to revive it.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit cfd280c912 ("net: sync some IP headers with glibc") changed a set of
define's to an enum (with no explanation why) which introduced a bug
in module mip6 where aliases are generated using the IPPROTO_* defines;
mip6 doesn't load if require_module called with the aliases from
xfrm_get_type().
Reverting this change back to define's to fix the aliases.
modinfo mip6 (before this change)
alias: xfrm-type-10-IPPROTO_DSTOPTS
alias: xfrm-type-10-IPPROTO_ROUTING
modinfo mip6 (after this change)
alias: xfrm-type-10-43
alias: xfrm-type-10-60
Signed-off-by: Jan Moskyto Matejka <mq@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a static checker fix, but judging from the context then I think
hexidecimal 0x80 is intended here instead of decimal 80.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit efe4208f47:
'ipv6: make lookups simpler and faster' broke initialization of local source
address on accepted ipv6 sockets. Before the mentioned commit receive address
was copied along with the contents of ipv6_pinfo in sctp_v6_create_accept_sk.
Now when it is moved, it has to be copied separately.
This also fixes lksctp's ipv6 regression in a sense that test_getname_v6, TC5 -
'getsockname on a connected server socket' now passes.
Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nsn.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The submission of the interrupt transfer should be done after setting
the bit of WORK_ENABLE, otherwise the callback function would have
the opportunity to be returned directly.
Clear the bit of WORK_ENABLE before killing the interrupt transfer.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
bnx2x driver uses incorrect PF identifier to configure (in HW) the VF
interrupt scheme; As a result, in multi-function mode the configuration
for PFs with a high index (4+) will overflow and the PF will erroneously
configure a single ISR scheme for its VFs.
As a result, if such a VF uses multiple queues, interrupt generation will
stop after VF receives an Rx packet or sends a Tx packet on a queue
other than queue[0].
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
